Publication Details
The Zero Resource Speech Challenge 2020: Discovering discrete subword and word units
Karadayi Julien (INRIA)
Bernard Mathieu (INRIA)
Cao Xuan-Nga (INRIA)
Algayres Robin (INRIA)
Ondel Lucas Antoine Francois, Mgr., Ph.D. (FIT BUT)
Besacier Laurent (UGA)
Sakti Sakriani (RIKEN-AIP)
Dupoux Emmanuel (ENS)
zero resource speech technology, speech synthesis, acoustic unit discovery, spoken term discovery, unsupervised learning
We present the Zero Resource Speech Challenge 2020, which aims at learning speech representations from raw audio signals without any labels. It combines the data sets and metrics from two previous benchmarks (2017 and 2019) and features two tasks which tap into two levels of speech representation. The first task is to discover low bit-rate subword representations that optimize the quality of speech synthesis; the second one is to discover word-like units from unsegmented raw speech. We present the results of the twenty submitted models and discuss the implications of the main findings for unsupervised speech learning.
@INPROCEEDINGS{FITPUB12380,
author = "Ewan Dunbar and Julien Karadayi and Mathieu Bernard and Xuan-Nga Cao and Robin Algayres and Francois Antoine Lucas Ondel and Laurent Besacier and Sakriani Sakti and Emmanuel Dupoux",
title = "The Zero Resource Speech Challenge 2020: Discovering discrete subword and word units",
pages = "4831--4835",
booktitle = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",
journal = "Proceedings of Interspeech - on-line",
volume = 2020,
number = 10,
year = 2020,
location = "Shanghai, CN",
publisher = "International Speech Communication Association",
ISSN = "1990-9772",
doi = "10.21437/Interspeech.2020-2743",
language = "english",
url = "https://www.fit.vut.cz/research/publication/12380"
}